Autonomous Vehicle Emergency Destination Selection Under Traffic Constraints
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional autonomous driving systems fail to consider the state of the autonomous driving subsystem and surrounding traffic conditions when responding to emergencies, leading to increased congestion due to inadequate destination selection for emergency stops or parking.
Innovation Solution
A method and system that generate a destination for emergency responses by using sensor data to create candidate destinations based on the autonomous vehicle's perception information, excluding risk areas, and selecting the destination with the maximum vertical movement distance to minimize collisions and optimize traffic flow.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If the autonomous vehicle immediately decelerates and stops on the relevant lane when takeover by driver does not occur, then the emergency response is prompt, but traffic congestion increases due to not considering surrounding traffic conditions
Solution Approach 1:
The system performs preliminary analysis of surrounding traffic conditions and subsystem states before executing emergency stop. It generates multiple candidate destinations and evaluates them using a scoring function that considers traffic conditions, subsystem controllability, and safety. This preliminary planning allows the vehicle to select an optimal stop location that minimizes traffic disruption while still responding promptly to emergencies.
Solution Approach 2:
The system dynamically adjusts the emergency response strategy based on real-time traffic conditions and subsystem states. Instead of a fixed immediate stop, it generates multiple candidate destinations and selects the optimal one based on current conditions. This dynamic approach allows the vehicle to maintain prompt emergency response while adapting to surrounding traffic to minimize congestion.
2Device complexity
If the autonomous vehicle selects destination without considering subsystem state and traffic conditions, then the destination selection process is simple, but collision risk increases
Solution Approach 1:
The destination selection process is segmented into distinct evaluation dimensions: traffic condition assessment, subsystem state analysis, candidate destination generation, and scoring-based selection. Each dimension is handled separately with specific evaluation criteria, making the complex process more manageable and reliable. The system divides the problem into perceivable factors, controllable factors, and scoring functions that can be independently optimized.
Solution Approach 2:
The system implements feedback mechanisms by continuously monitoring subsystem states (brake control, heading control, movable distance) and surrounding traffic conditions. This feedback is integrated into the destination scoring function, which evaluates each candidate destination based on current system state and environmental conditions. The feedback loop ensures that the selected destination is both safe and achievable given the current subsystem capabilities.
3Measurement precision
If the autonomous vehicle performs comprehensive analysis of traffic conditions and subsystem state, then destination selection accuracy improves, but computational time increases
Solution Approach 1:
The system performs comprehensive analysis of traffic conditions and subsystem states but applies selective weighting through the scoring function. Not all factors are equally important in every situation - the scoring mechanism prioritizes critical factors (such as collision risk and subsystem controllability) while still considering secondary factors. This partial emphasis approach maintains high accuracy by focusing computational resources on the most influential parameters.
Solution Approach 2:
The system changes parameters dynamically by adjusting the weights and thresholds in the scoring function based on the specific emergency situation. Different subsystem states and traffic conditions trigger different parameter configurations, allowing the system to adapt its analysis depth and focus. This parameter adaptation enables accurate destination selection while optimizing computational efficiency for each specific scenario.
Data Source
AI summary
Provided are a method and system for generating a destination for an emergency response of an autonomous vehicle of an autonomous driving system. A method of generating a destination of an autonomous vehicle according to the present invention includes generating forward perception information based on data collected from a sensor mounted on the autonomous vehicle, setting a destination generation area based on the forward perception information, generating a candidate destination in the destination generation area based on the forward perception information and a current heading range of the autonomous vehicle, and when the candidate destination is provided as a plurality of candidate destinations, selecting one destination from among the candidate destinations based on a maximum vertical movement distance of each of the candidate destinations.